2025-10-28 08:10:23 -07:00
|
|
|
use anyhow::Result;
|
fix: separate `codex mcp` into `codex mcp-server` and `codex app-server` (#4471)
This is a very large PR with some non-backwards-compatible changes.
Historically, `codex mcp` (or `codex mcp serve`) started a JSON-RPC-ish
server that had two overlapping responsibilities:
- Running an MCP server, providing some basic tool calls.
- Running the app server used to power experiences such as the VS Code
extension.
This PR aims to separate these into distinct concepts:
- `codex mcp-server` for the MCP server
- `codex app-server` for the "application server"
Note `codex mcp` still exists because it already has its own subcommands
for MCP management (`list`, `add`, etc.)
The MCP logic continues to live in `codex-rs/mcp-server` whereas the
refactored app server logic is in the new `codex-rs/app-server` folder.
Note that most of the existing integration tests in
`codex-rs/mcp-server/tests/suite` were actually for the app server, so
all the tests have been moved with the exception of
`codex-rs/mcp-server/tests/suite/mod.rs`.
Because this is already a large diff, I tried not to change more than I
had to, so `codex-rs/app-server/tests/common/mcp_process.rs` still uses
the name `McpProcess` for now, but I will do some mechanical renamings
to things like `AppServer` in subsequent PRs.
While `mcp-server` and `app-server` share some overlapping functionality
(like reading streams of JSONL and dispatching based on message types)
and some differences (completely different message types), I ended up
doing a bit of copypasta between the two crates, as both have somewhat
similar `message_processor.rs` and `outgoing_message.rs` files for now,
though I expect them to diverge more in the near future.
One material change is that of the initialize handshake for `codex
app-server`, as we no longer use the MCP types for that handshake.
Instead, we update `codex-rs/protocol/src/mcp_protocol.rs` to add an
`Initialize` variant to `ClientRequest`, which takes the `ClientInfo`
object we need to update the `USER_AGENT_SUFFIX` in
`codex-rs/app-server/src/message_processor.rs`.
One other material change is in
`codex-rs/app-server/src/codex_message_processor.rs` where I eliminated
a use of the `send_event_as_notification()` method I am generally trying
to deprecate (because it blindly maps an `EventMsg` into a
`JSONNotification`) in favor of `send_server_notification()`, which
takes a `ServerNotification`, as that is intended to be a custom enum of
all notification types supported by the app server. So to make this
update, I had to introduce a new variant of `ServerNotification`,
`SessionConfigured`, which is a non-backwards compatible change with the
old `codex mcp`, and clients will have to be updated after the next
release that contains this PR. Note that
`codex-rs/app-server/tests/suite/list_resume.rs` also had to be update
to reflect this change.
I introduced `codex-rs/utils/json-to-toml/src/lib.rs` as a small utility
crate to avoid some of the copying between `mcp-server` and
`app-server`.
2025-09-30 00:06:18 -07:00
|
|
|
use app_test_support::McpProcess;
|
|
|
|
|
use app_test_support::to_response;
|
fix: remove mcp-types from app server protocol (#4537)
We continue the separation between `codex app-server` and `codex
mcp-server`.
In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.
Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.
We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.
Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.
2025-09-30 19:16:26 -07:00
|
|
|
use codex_app_server_protocol::CancelLoginChatGptParams;
|
|
|
|
|
use codex_app_server_protocol::CancelLoginChatGptResponse;
|
|
|
|
|
use codex_app_server_protocol::GetAuthStatusParams;
|
|
|
|
|
use codex_app_server_protocol::GetAuthStatusResponse;
|
2025-10-20 08:50:54 -07:00
|
|
|
use codex_app_server_protocol::JSONRPCError;
|
fix: remove mcp-types from app server protocol (#4537)
We continue the separation between `codex app-server` and `codex
mcp-server`.
In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.
Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.
We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.
Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.
2025-09-30 19:16:26 -07:00
|
|
|
use codex_app_server_protocol::JSONRPCResponse;
|
|
|
|
|
use codex_app_server_protocol::LoginChatGptResponse;
|
|
|
|
|
use codex_app_server_protocol::LogoutChatGptResponse;
|
|
|
|
|
use codex_app_server_protocol::RequestId;
|
2025-10-27 19:41:49 -07:00
|
|
|
use codex_core::auth::AuthCredentialsStoreMode;
|
2025-09-11 09:16:34 -07:00
|
|
|
use codex_login::login_with_api_key;
|
2025-10-24 18:31:24 -05:00
|
|
|
use serial_test::serial;
|
2025-10-28 08:10:23 -07:00
|
|
|
use std::path::Path;
|
|
|
|
|
use std::time::Duration;
|
2025-08-22 13:10:11 -07:00
|
|
|
use tempfile::TempDir;
|
|
|
|
|
use tokio::time::timeout;
|
|
|
|
|
|
|
|
|
|
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
|
|
|
|
|
|
|
|
|
// Helper to create a config.toml; mirrors create_conversation.rs
|
|
|
|
|
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
|
|
|
|
|
let config_toml = codex_home.join("config.toml");
|
|
|
|
|
std::fs::write(
|
|
|
|
|
config_toml,
|
|
|
|
|
r#"
|
|
|
|
|
model = "mock-model"
|
|
|
|
|
approval_policy = "never"
|
|
|
|
|
sandbox_mode = "danger-full-access"
|
|
|
|
|
|
|
|
|
|
model_provider = "mock_provider"
|
|
|
|
|
|
|
|
|
|
[model_providers.mock_provider]
|
|
|
|
|
name = "Mock provider for test"
|
|
|
|
|
base_url = "http://127.0.0.1:0/v1"
|
|
|
|
|
wire_api = "chat"
|
|
|
|
|
request_max_retries = 0
|
|
|
|
|
stream_max_retries = 0
|
|
|
|
|
"#,
|
|
|
|
|
)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
2025-10-28 08:10:23 -07:00
|
|
|
async fn logout_chatgpt_removes_auth() -> Result<()> {
|
|
|
|
|
let codex_home = TempDir::new()?;
|
|
|
|
|
create_config_toml(codex_home.path())?;
|
2025-10-27 19:41:49 -07:00
|
|
|
login_with_api_key(
|
|
|
|
|
codex_home.path(),
|
|
|
|
|
"sk-test-key",
|
|
|
|
|
AuthCredentialsStoreMode::File,
|
2025-10-28 08:10:23 -07:00
|
|
|
)?;
|
2025-08-22 13:10:11 -07:00
|
|
|
assert!(codex_home.path().join("auth.json").exists());
|
|
|
|
|
|
2025-10-28 08:10:23 -07:00
|
|
|
let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
|
|
|
|
|
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
|
|
|
|
|
|
|
|
|
let id = mcp.send_logout_chat_gpt_request().await?;
|
2025-08-22 13:10:11 -07:00
|
|
|
let resp: JSONRPCResponse = timeout(
|
|
|
|
|
DEFAULT_READ_TIMEOUT,
|
|
|
|
|
mcp.read_stream_until_response_message(RequestId::Integer(id)),
|
|
|
|
|
)
|
2025-10-28 08:10:23 -07:00
|
|
|
.await??;
|
|
|
|
|
let _ok: LogoutChatGptResponse = to_response(resp)?;
|
2025-08-22 13:10:11 -07:00
|
|
|
|
|
|
|
|
assert!(
|
|
|
|
|
!codex_home.path().join("auth.json").exists(),
|
|
|
|
|
"auth.json should be deleted"
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
// Verify status reflects signed-out state.
|
|
|
|
|
let status_id = mcp
|
|
|
|
|
.send_get_auth_status_request(GetAuthStatusParams {
|
|
|
|
|
include_token: Some(true),
|
|
|
|
|
refresh_token: Some(false),
|
|
|
|
|
})
|
2025-10-28 08:10:23 -07:00
|
|
|
.await?;
|
2025-08-22 13:10:11 -07:00
|
|
|
let status_resp: JSONRPCResponse = timeout(
|
|
|
|
|
DEFAULT_READ_TIMEOUT,
|
|
|
|
|
mcp.read_stream_until_response_message(RequestId::Integer(status_id)),
|
|
|
|
|
)
|
2025-10-28 08:10:23 -07:00
|
|
|
.await??;
|
|
|
|
|
let status: GetAuthStatusResponse = to_response(status_resp)?;
|
2025-08-22 13:10:11 -07:00
|
|
|
assert_eq!(status.auth_method, None);
|
|
|
|
|
assert_eq!(status.auth_token, None);
|
2025-10-28 08:10:23 -07:00
|
|
|
Ok(())
|
2025-08-22 13:10:11 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
2025-10-24 18:31:24 -05:00
|
|
|
// Serialize tests that launch the login server since it binds to a fixed port.
|
|
|
|
|
#[serial(login_port)]
|
2025-10-28 08:10:23 -07:00
|
|
|
async fn login_and_cancel_chatgpt() -> Result<()> {
|
|
|
|
|
let codex_home = TempDir::new()?;
|
|
|
|
|
create_config_toml(codex_home.path())?;
|
|
|
|
|
|
|
|
|
|
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
|
|
|
|
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
|
|
|
|
|
|
|
|
|
let login_id = mcp.send_login_chat_gpt_request().await?;
|
2025-08-22 13:10:11 -07:00
|
|
|
let login_resp: JSONRPCResponse = timeout(
|
|
|
|
|
DEFAULT_READ_TIMEOUT,
|
|
|
|
|
mcp.read_stream_until_response_message(RequestId::Integer(login_id)),
|
|
|
|
|
)
|
2025-10-28 08:10:23 -07:00
|
|
|
.await??;
|
|
|
|
|
let login: LoginChatGptResponse = to_response(login_resp)?;
|
2025-08-22 13:10:11 -07:00
|
|
|
|
|
|
|
|
let cancel_id = mcp
|
|
|
|
|
.send_cancel_login_chat_gpt_request(CancelLoginChatGptParams {
|
|
|
|
|
login_id: login.login_id,
|
|
|
|
|
})
|
2025-10-28 08:10:23 -07:00
|
|
|
.await?;
|
2025-08-22 13:10:11 -07:00
|
|
|
let cancel_resp: JSONRPCResponse = timeout(
|
|
|
|
|
DEFAULT_READ_TIMEOUT,
|
|
|
|
|
mcp.read_stream_until_response_message(RequestId::Integer(cancel_id)),
|
|
|
|
|
)
|
2025-10-28 08:10:23 -07:00
|
|
|
.await??;
|
|
|
|
|
let _ok: CancelLoginChatGptResponse = to_response(cancel_resp)?;
|
2025-08-22 13:10:11 -07:00
|
|
|
|
|
|
|
|
// Optionally observe the completion notification; do not fail if it races.
|
|
|
|
|
let maybe_note = timeout(
|
|
|
|
|
Duration::from_secs(2),
|
|
|
|
|
mcp.read_stream_until_notification_message("codex/event/login_chat_gpt_complete"),
|
|
|
|
|
)
|
|
|
|
|
.await;
|
|
|
|
|
if maybe_note.is_err() {
|
|
|
|
|
eprintln!("warning: did not observe login_chat_gpt_complete notification after cancel");
|
|
|
|
|
}
|
2025-10-28 08:10:23 -07:00
|
|
|
Ok(())
|
2025-08-22 13:10:11 -07:00
|
|
|
}
|
2025-10-20 08:50:54 -07:00
|
|
|
|
|
|
|
|
fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
|
|
|
|
|
let config_toml = codex_home.join("config.toml");
|
|
|
|
|
let contents = format!(
|
|
|
|
|
r#"
|
|
|
|
|
model = "mock-model"
|
|
|
|
|
approval_policy = "never"
|
|
|
|
|
sandbox_mode = "danger-full-access"
|
|
|
|
|
forced_login_method = "{forced_method}"
|
|
|
|
|
"#
|
|
|
|
|
);
|
|
|
|
|
std::fs::write(config_toml, contents)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn create_config_toml_forced_workspace(
|
|
|
|
|
codex_home: &Path,
|
|
|
|
|
workspace_id: &str,
|
|
|
|
|
) -> std::io::Result<()> {
|
|
|
|
|
let config_toml = codex_home.join("config.toml");
|
|
|
|
|
let contents = format!(
|
|
|
|
|
r#"
|
|
|
|
|
model = "mock-model"
|
|
|
|
|
approval_policy = "never"
|
|
|
|
|
sandbox_mode = "danger-full-access"
|
|
|
|
|
forced_chatgpt_workspace_id = "{workspace_id}"
|
|
|
|
|
"#
|
|
|
|
|
);
|
|
|
|
|
std::fs::write(config_toml, contents)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
2025-10-28 08:10:23 -07:00
|
|
|
async fn login_chatgpt_rejected_when_forced_api() -> Result<()> {
|
|
|
|
|
let codex_home = TempDir::new()?;
|
|
|
|
|
create_config_toml_forced_login(codex_home.path(), "api")?;
|
|
|
|
|
|
|
|
|
|
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
|
|
|
|
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
|
|
|
|
|
|
|
|
|
let request_id = mcp.send_login_chat_gpt_request().await?;
|
2025-10-20 08:50:54 -07:00
|
|
|
let err: JSONRPCError = timeout(
|
|
|
|
|
DEFAULT_READ_TIMEOUT,
|
|
|
|
|
mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
|
|
|
|
|
)
|
2025-10-28 08:10:23 -07:00
|
|
|
.await??;
|
2025-10-20 08:50:54 -07:00
|
|
|
|
|
|
|
|
assert_eq!(
|
|
|
|
|
err.error.message,
|
|
|
|
|
"ChatGPT login is disabled. Use API key login instead."
|
|
|
|
|
);
|
2025-10-28 08:10:23 -07:00
|
|
|
Ok(())
|
2025-10-20 08:50:54 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
2025-10-24 18:31:24 -05:00
|
|
|
// Serialize tests that launch the login server since it binds to a fixed port.
|
|
|
|
|
#[serial(login_port)]
|
2025-10-28 08:10:23 -07:00
|
|
|
async fn login_chatgpt_includes_forced_workspace_query_param() -> Result<()> {
|
|
|
|
|
let codex_home = TempDir::new()?;
|
|
|
|
|
create_config_toml_forced_workspace(codex_home.path(), "ws-forced")?;
|
|
|
|
|
|
|
|
|
|
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
|
|
|
|
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
|
|
|
|
|
|
|
|
|
let request_id = mcp.send_login_chat_gpt_request().await?;
|
2025-10-20 08:50:54 -07:00
|
|
|
let resp: JSONRPCResponse = timeout(
|
|
|
|
|
DEFAULT_READ_TIMEOUT,
|
|
|
|
|
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
|
|
|
|
|
)
|
2025-10-28 08:10:23 -07:00
|
|
|
.await??;
|
2025-10-20 08:50:54 -07:00
|
|
|
|
2025-10-28 08:10:23 -07:00
|
|
|
let login: LoginChatGptResponse = to_response(resp)?;
|
2025-10-20 08:50:54 -07:00
|
|
|
assert!(
|
|
|
|
|
login.auth_url.contains("allowed_workspace_id=ws-forced"),
|
|
|
|
|
"auth URL should include forced workspace"
|
|
|
|
|
);
|
2025-10-28 08:10:23 -07:00
|
|
|
Ok(())
|
2025-10-20 08:50:54 -07:00
|
|
|
}
|